MCP server · Research
Scholar Feed MCP server
by YGao2005
Lets your AI search 600k+ computer science and AI papers, follow citations, and export BibTeX.

Scholar Feed is a helper that connects your AI assistant to a big library of computer science and AI research papers. Instead of a flat list of results, it can rank papers by relevance, citation count, or rising impact, and trace who cites whom. It is handy if you read papers for work, study, or a literature review.
What is an MCP server? The 30-second version
On its own, your AI can only chat with you using what it already learned. An MCP server is a small helper program that gives your AI a new skill or a connection to an outside service. This one connects your AI to Scholar Feed, a daily-updated index of arXiv papers. Once it is connected, you can just ask your AI to find, compare, or summarize papers, and it will go look them up for you.
What this MCP server does
You ask your AI a question in plain words, like finding recent papers on a topic. Your AI passes that request to this helper, which searches the Scholar Feed index of 600k+ papers. The helper can also follow citation links, pull the full text of a paper by section, or export a BibTeX entry. Then your AI hands you back a ranked list, a summary, or a file you can use.
Click to zoomWhat you can do with it
- Search papers by topic, category, or novelty score
- Find papers similar to one you already have
- Trace who a paper cites and who cites it
- Read a paper's full text by section
- Export BibTeX entries for your reference manager
- Find researchers working on a topic
- Save papers and collections to your own library
Try asking your AI
- “Search for recent papers on test-time compute scaling”
- “Find papers similar to 2401.04088 and export their BibTeX”
- “What's trending in cs.CV this week? Summarize the top 3.”
- “Who are the top researchers working on efficient LLM inference?”
What it gives back to you
You get back a ranked list of papers with titles, authors, years, categories, and links. You can also get a short summary of a paper, its citation lineage, or a BibTeX block you can copy. If you ask for a synthesis over your saved papers, you get an answer with citations to those papers. Everything shows up right in your chat.
Before you start
What you need
- An MCP-compatible client like Claude Desktop, Claude Code, or Cursor
- Node.js installed so the npx command can run
- Optional: a free Scholar Feed API key for a higher monthly quota
Good to know
The library tools can change your saved papers, collections, and watches, so check before letting your AI delete or overwrite anything.
Install it with your AI
Add Scholar Feed MCP server to your AI, no technical skills needed
You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.
Sign in to get the install prompt
Members get a ready-made prompt that lets the Claude desktop app check Scholar Feed MCP server, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,066 MCP servers here for you.
Who it's for
Researchers, students, and engineers who read computer science or AI papers and want quick search, citation tracing, and BibTeX export without leaving their AI assistant.





